{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:UGGKUGZRLHXZVM5A6AYV63WBK2","short_pith_number":"pith:UGGKUGZR","canonical_record":{"source":{"id":"1909.05304","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LO","submitted_at":"2019-09-11T18:48:02Z","cross_cats_sorted":["cs.LG","cs.SY","eess.SY","stat.ML"],"title_canon_sha256":"1e2ea6d5f73172053fe8f871616b633be28ca342aafdd1c9c828d23242258bf2","abstract_canon_sha256":"faaeb3240b3f7907b3ea5b855c0161d68841178f44a88005953656c4e93353d7"},"schema_version":"1.0"},"canonical_sha256":"a18caa1b3159ef9ab3a0f0315f6ec156a1407a298aaf28a43724f54fd0501b47","source":{"kind":"arxiv","id":"1909.05304","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.05304","created_at":"2026-07-05T00:04:11Z"},{"alias_kind":"arxiv_version","alias_value":"1909.05304v1","created_at":"2026-07-05T00:04:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.05304","created_at":"2026-07-05T00:04:11Z"},{"alias_kind":"pith_short_12","alias_value":"UGGKUGZRLHXZ","created_at":"2026-07-05T00:04:11Z"},{"alias_kind":"pith_short_16","alias_value":"UGGKUGZRLHXZVM5A","created_at":"2026-07-05T00:04:11Z"},{"alias_kind":"pith_short_8","alias_value":"UGGKUGZR","created_at":"2026-07-05T00:04:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:UGGKUGZRLHXZVM5A6AYV63WBK2","target":"record","payload":{"canonical_record":{"source":{"id":"1909.05304","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LO","submitted_at":"2019-09-11T18:48:02Z","cross_cats_sorted":["cs.LG","cs.SY","eess.SY","stat.ML"],"title_canon_sha256":"1e2ea6d5f73172053fe8f871616b633be28ca342aafdd1c9c828d23242258bf2","abstract_canon_sha256":"faaeb3240b3f7907b3ea5b855c0161d68841178f44a88005953656c4e93353d7"},"schema_version":"1.0"},"canonical_sha256":"a18caa1b3159ef9ab3a0f0315f6ec156a1407a298aaf28a43724f54fd0501b47","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:04:11.649117Z","signature_b64":"YtRcZs9SZpXDHGndH7q4JlBtEHnCfxf+JQa74MJdgMgWSdzuHKx0gmuvoEMIgB+3lPEKgHonE5IweUGT0UCjBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a18caa1b3159ef9ab3a0f0315f6ec156a1407a298aaf28a43724f54fd0501b47","last_reissued_at":"2026-07-05T00:04:11.648621Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:04:11.648621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1909.05304","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:04:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yMWjT5Gi8TT35WTvK6t61hFT4WPaqFzJqRc2fVJcjOYHMYcYk0nyQq+K0AkDBnly4PbLcY0BSn/vTIAWtwxhCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:15:46.057489Z"},"content_sha256":"3f86849ebb252665acbe69f36e8a462828d35bb85f0ced29a1f9f81c867989cb","schema_version":"1.0","event_id":"sha256:3f86849ebb252665acbe69f36e8a462828d35bb85f0ced29a1f9f81c867989cb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:UGGKUGZRLHXZVM5A6AYV63WBK2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning for Temporal Logic Control Synthesis with Probabilistic Satisfaction Guarantees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY","eess.SY","stat.ML"],"primary_cat":"cs.LO","authors_text":"Alessandro Abate, Daniel Kroening, George J. Pappas, Insup Lee, Mohammadhosein Hasanbeig, Yiannis Kantaros","submitted_at":"2019-09-11T18:48:02Z","abstract_excerpt":"Reinforcement Learning (RL) has emerged as an efficient method of choice for solving complex sequential decision making problems in automatic control, computer science, economics, and biology. In this paper we present a model-free RL algorithm to synthesize control policies that maximize the probability of satisfying high-level control objectives given as Linear Temporal Logic (LTL) formulas. Uncertainty is considered in the workspace properties, the structure of the workspace, and the agent actions, giving rise to a Probabilistically-Labeled Markov Decision Process (PL-MDP) with unknown graph"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.05304","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1909.05304/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:04:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i3oTJjuIml/37nlvE7x4Et1qA1DL8AOb801G+/68294HQ60CSBRIQOUP6kW0sv6bIq/u80iOrB/p8z3P7sYxCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:15:46.057886Z"},"content_sha256":"793b6690acc54dcf9097dcb3c117b557dcbc8d0cbba257a08ef260a4d5a56e0d","schema_version":"1.0","event_id":"sha256:793b6690acc54dcf9097dcb3c117b557dcbc8d0cbba257a08ef260a4d5a56e0d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UGGKUGZRLHXZVM5A6AYV63WBK2/bundle.json","state_url":"https://pith.science/pith/UGGKUGZRLHXZVM5A6AYV63WBK2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UGGKUGZRLHXZVM5A6AYV63WBK2/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T05:15:46Z","links":{"resolver":"https://pith.science/pith/UGGKUGZRLHXZVM5A6AYV63WBK2","bundle":"https://pith.science/pith/UGGKUGZRLHXZVM5A6AYV63WBK2/bundle.json","state":"https://pith.science/pith/UGGKUGZRLHXZVM5A6AYV63WBK2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UGGKUGZRLHXZVM5A6AYV63WBK2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:UGGKUGZRLHXZVM5A6AYV63WBK2","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"faaeb3240b3f7907b3ea5b855c0161d68841178f44a88005953656c4e93353d7","cross_cats_sorted":["cs.LG","cs.SY","eess.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LO","submitted_at":"2019-09-11T18:48:02Z","title_canon_sha256":"1e2ea6d5f73172053fe8f871616b633be28ca342aafdd1c9c828d23242258bf2"},"schema_version":"1.0","source":{"id":"1909.05304","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.05304","created_at":"2026-07-05T00:04:11Z"},{"alias_kind":"arxiv_version","alias_value":"1909.05304v1","created_at":"2026-07-05T00:04:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.05304","created_at":"2026-07-05T00:04:11Z"},{"alias_kind":"pith_short_12","alias_value":"UGGKUGZRLHXZ","created_at":"2026-07-05T00:04:11Z"},{"alias_kind":"pith_short_16","alias_value":"UGGKUGZRLHXZVM5A","created_at":"2026-07-05T00:04:11Z"},{"alias_kind":"pith_short_8","alias_value":"UGGKUGZR","created_at":"2026-07-05T00:04:11Z"}],"graph_snapshots":[{"event_id":"sha256:793b6690acc54dcf9097dcb3c117b557dcbc8d0cbba257a08ef260a4d5a56e0d","target":"graph","created_at":"2026-07-05T00:04:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1909.05304/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) has emerged as an efficient method of choice for solving complex sequential decision making problems in automatic control, computer science, economics, and biology. In this paper we present a model-free RL algorithm to synthesize control policies that maximize the probability of satisfying high-level control objectives given as Linear Temporal Logic (LTL) formulas. Uncertainty is considered in the workspace properties, the structure of the workspace, and the agent actions, giving rise to a Probabilistically-Labeled Markov Decision Process (PL-MDP) with unknown graph","authors_text":"Alessandro Abate, Daniel Kroening, George J. Pappas, Insup Lee, Mohammadhosein Hasanbeig, Yiannis Kantaros","cross_cats":["cs.LG","cs.SY","eess.SY","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LO","submitted_at":"2019-09-11T18:48:02Z","title":"Reinforcement Learning for Temporal Logic Control Synthesis with Probabilistic Satisfaction Guarantees"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.05304","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3f86849ebb252665acbe69f36e8a462828d35bb85f0ced29a1f9f81c867989cb","target":"record","created_at":"2026-07-05T00:04:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"faaeb3240b3f7907b3ea5b855c0161d68841178f44a88005953656c4e93353d7","cross_cats_sorted":["cs.LG","cs.SY","eess.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LO","submitted_at":"2019-09-11T18:48:02Z","title_canon_sha256":"1e2ea6d5f73172053fe8f871616b633be28ca342aafdd1c9c828d23242258bf2"},"schema_version":"1.0","source":{"id":"1909.05304","kind":"arxiv","version":1}},"canonical_sha256":"a18caa1b3159ef9ab3a0f0315f6ec156a1407a298aaf28a43724f54fd0501b47","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a18caa1b3159ef9ab3a0f0315f6ec156a1407a298aaf28a43724f54fd0501b47","first_computed_at":"2026-07-05T00:04:11.648621Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:04:11.648621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YtRcZs9SZpXDHGndH7q4JlBtEHnCfxf+JQa74MJdgMgWSdzuHKx0gmuvoEMIgB+3lPEKgHonE5IweUGT0UCjBg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:04:11.649117Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.05304","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3f86849ebb252665acbe69f36e8a462828d35bb85f0ced29a1f9f81c867989cb","sha256:793b6690acc54dcf9097dcb3c117b557dcbc8d0cbba257a08ef260a4d5a56e0d"],"state_sha256":"d9d0c88200fd47ba6a8abd8e8d32897f5bd1f682f4c438a9396c1621904e7f62"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PQStzYpN4myUf1zTLmGKGqlxYm9uMVlOMJTLVh6wl08g1/MQGXzpta3c7F5KbK738xVBAgw0AOCGjV2ADUSXDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T05:15:46.060485Z","bundle_sha256":"dfe8f878b1cba7e7596682ec35051d9c1dcb4a52628f0b7d0fe6723b660e1d78"}}